Training in progress, step 4

config.json

@@ -1,71 +1,37 @@
 {
+  "_attn_implementation_autoset": true,
+  "adapters": [
+    "lnn"
+  ],
   "architectures": [
     "Qwen2ForCausalLM"
   ],
-  "model_type": "qwen2",
-  "vocab_size": 37524,
+  "bos_token_id": 2,
+  "chunk_size_feed_forward": 64,
   "d_model": 2048,
+  "do_sample": true,
+  "dropout": 0.1,
+  "eos_token_id": 3,
+  "hidden_size": 2048,
+  "intermediate_size": 8192,
+  "max_length": 512,
+  "max_seq": 4096,
+  "min_length": 64,
+  "model_type": "symbiotic-llm",
   "n_heads": 32,
   "n_layers": 16,
-  "max_seq": 4096,
+  "no_repeat_ngram_size": 1,
+  "num_attention_heads": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
   "rope_base": 1000000.0,
-  "dropout": 0.1,
-  "adapters": [
-    "lnn"
-  ],
   "tie_embed": true,
-  "use_flash": false,
-  "return_dict": true,
-  "output_hidden_states": false,
-  "output_attentions": false,
-  "torchscript": false,
-  "torch_dtype": "float16",
-  "use_bfloat16": false,
-  "tf_legacy_loss": false,
-  "pruned_heads": {},
-  "tie_word_embeddings": true,
-  "chunk_size_feed_forward": 64,
-  "is_encoder_decoder": false,
-  "is_decoder": false,
-  "add_cross_attention": false,
-  "cross_attention_hidden_size": null,
-  "tie_encoder_decoder": false,
-  "max_length": 512,
-  "min_length": 64,
-  "do_sample": true,
-  "early_stopping": false,
-  "num_beams": 1,
-  "num_beam_groups": 1,
-  "diversity_penalty": 0.0,
-  "temperature": 1.0,
-  "top_k": 50,
+  "tokenizer_class": "PreTrainedTokenizerFast",
   "top_p": 0.9,
+  "torch_dtype": "float16",
+  "transformers_version": "4.51.3",
   "typical_p": 0.95,
-  "repetition_penalty": 1.0,
-  "length_penalty": 1.0,
-  "no_repeat_ngram_size": 1,
-  "encoder_no_repeat_ngram_size": 0,
-  "bad_words_ids": null,
-  "num_return_sequences": 1,
-  "output_scores": false,
-  "return_dict_in_generate": false,
-  "forced_bos_token_id": null,
-  "forced_eos_token_id": null,
-  "remove_invalid_values": false,
-  "exponential_decay_length_penalty": null,
-  "suppress_tokens": null,
-  "begin_suppress_tokens": null,
-  "finetuning_task": null,
-  "tokenizer_class": "PreTrainedTokenizerFast",
-  "prefix": null,
-  "bos_token_id": 2,
-  "pad_token_id": 0,
-  "eos_token_id": 3,
-  "sep_token_id": null,
-  "decoder_start_token_id": null,
-  "task_specific_params": null,
-  "problem_type": null,
-  "_name_or_path": "",
-  "_attn_implementation_autoset": true,
-  "transformers_version": "4.51.3"
+  "use_flash": false,
+  "vocab_size": 37524
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7bb78bf0f1be59b347513a24d9485ebcbad1217ea0b042e1a99c0774f20a3eb
+size 14279060944

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27b65796bd11cacf21704d65ced17aaff7d6b567784c997fbefb6a628e49f499
-size 5713
+oid sha256:7b0ea490ecfa0dc942a6fb6fdb45d46dc2e2d861b2185117b6ccb32cae1f7a50
+size 5777